2025· International Journal of Applied Data Science & Modern Computing· 0 citations
TL;DR
This study proposes an LLM-powered knowledge management framework that combines Retrieval-Augmented Generation (RAG), semantic embeddings, enterprise-specific language models, and vector databases to transform enterprise data into actionable knowledge.
Abstract
Enterprise Knowledge Management Platforms (EKMPs) help organizations capture, organize, share, and utilize knowledge to improve decision-making and operational efficiency. Traditional knowledge management systems often face challenges such as data silos, unstructured information, limited contextual understanding, and ineffective search capabilities. The integration of Large Language Models (LLMs) addresses these limitations by enabling intelligent search, semantic understanding, automated content generation, and conversational interfaces. This study proposes an LLM-powered knowledge management framework that combines Retrieval-Augmented Generation (RAG), semantic embeddings, enterprise-specific language models, and vector databases to transform enterprise data into actionable knowledge. The framework includes data ingestion pipelines, knowledge repositories, embedding generation modules, retrieval systems, and conversational AI interfaces while emphasizing security, privacy, governance, scalability, and explainability. It also addresses challenges such as hallucination reduction, domain adaptation, and knowledge freshness. Experimental results demonstrate that LLM-based systems significantly improve retrieval accuracy, response relevance, knowledge reuse, and user satisfaction compared with traditional keyword-based approaches. These advancements enhance employee productivity, decision quality, collaboration, and innovation, positioning LLM-driven knowledge management systems as a key enabler of enterprise digital transformation.
A literature-based architectural framework for reliable knowledge retrieval systems that separates external knowledge management from LLM-based reasoning and generation is developed and indicates that reliable LLM deployment should be treated as an end-to-end architectural problem rather than solely a model-performance problem.
Bharat Kumar Reddy Karumuri· International Journal of Eng...· 0 citations
Artificial Intelligence (AI) and Large Language Models (LLMs) have significantly transformed knowledge management by enabling intelligent, context-aware, and automated information access. However, standalone LLMs often suffer from limitations such as outdated knowledge, hallucinated responses, lack of domain-specific expertise, and limited transparency, reducing their reliability in enterprise and research applications. Retrieval-Augmented Generation (RAG) has emerged as an effective solution by combining language models with external knowledge retrieval, allowing responses to be generated using up-to-date and relevant information. This study proposes a comprehensive Retrieval-Augmented Generation framework for intelligent knowledge management systems. The framework integrates document acquisition, preprocessing, semantic embedding generation, vector database indexing, document retrieval, prompt augmentation, LLM-based response generation, response validation, and continuous knowledge base updates. It supports diverse knowledge sources, including enterprise databases, technical documents, digital libraries, and research repositories, while incorporating sparse, dense, hybrid retrieval, and neural reranking techniques to improve retrieval accuracy. The proposed framework is evaluated using retrieval precision, recall, F1-score, response relevance, latency, grounding accuracy, and user satisfaction. Results demonstrate improved semantic understanding, reduced hallucinations, enhanced factual correctness, and real-time knowledge updates compared with conventional keyword-based knowledge management systems. The study also discusses future directions, including multimodal RAG, graph-enhanced retrieval, federated knowledge management, continual learning, and autonomous enterprise knowledge assistants, establishing RAG as a robust foundation for trustworthy and intelligent knowledge-driven AI systems.
Louis Pouzin, J. Arsac· International Journal of Mod...· 0 citations
This study presents a conceptual framework that combines semantic retrieval, intelligent reasoning, automated literature analysis, and workflow orchestration, demonstrating how LLM-powered systems can transform scientific research into scalable, accurate, ethical, and collaborative knowledge discovery processes.
Narendra Karmarkar, Iyengar P. K.· International Journal of Eme...· 0 citations
It is demonstrated that integrating semantic retrieval with grounded LLM generation can improve knowledge accessibility, transparency, and reliability for AI-assisted decision support in public organizations.
Yohanes Bowo Widodo· International Journal of Eng...· 0 citations
Results indicate that LLM-augmented analytics on a converged Oracle 26AI platform can reduce average analytical query resolution time by approximately 60 percent relative to traditional BI report cycles, achieve semantic retrieval precision above 90 percent for enterprise knowledge corpora, and reduce generative output hallucination rates by more than half when grounding is enforced through in-database retrieval.
Enterprise Knowledge Management (EKM) plays a vital role in leveraging organizational knowledge, improving decision-making, and maintaining competitive advantage. Traditional knowledge management systems struggle with scalability, real-time adaptability, and contextual understanding. AI-driven digital assistants address these limitations by using technologies like Natural Language Processing (NLP), deep learning, and knowledge graphs to enable intelligent automation and semantic understanding. These assistants support conversational interactions, making knowledge access and contribution more intuitive. The study proposes a modular architecture with components such as data ingestion, semantic processing, knowledge repositories, and user interfaces, enhanced by reinforcement learning for continuous improvement. Hybrid models combining rule-based and learning-based approaches improve reliability and interpretability. Findings show that AI-based assistants enhance knowledge retrieval accuracy, reduce response time, and increase user satisfaction. They are widely applicable in areas like customer support, internal knowledge discovery, and decision support. Overall, AI-powered digital assistants improve efficiency and promote knowledge democratization, with future research focusing on explainability, ethical AI use, and integration of multimodal data.
Rebecca Green· International Journal of Art...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
